Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words compared with than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     соответствии
    0.85
     يتع
    0.79
    ）：
    0.77
     sadece
    0.75
    翀
    0.75
     uniquement
    0.74
     yalnızca
    0.74
    ogliamo
    0.73
    最初に
    0.72
     Grâce
    0.72
    POSITIVE LOGITS
     than
    3.80
     Than
    2.77
    than
    2.75
     niż
    2.48
    Than
    2.48
     än
    2.32
     kuin
    2.31
     decât
    2.04
     compared
    2.01
     než
    1.95
    Act Density 0.319%

    No Known Activations